{"id":"https://openalex.org/W4412722584","doi":"https://doi.org/10.1109/tpami.2025.3593543","title":"Towards Universal Modal Tracking With Online Dense Temporal Token Learning","display_name":"Towards Universal Modal Tracking With Online Dense Temporal Token Learning","publication_year":2025,"publication_date":"2025-07-29","ids":{"openalex":"https://openalex.org/W4412722584","doi":"https://doi.org/10.1109/tpami.2025.3593543","pmid":"https://pubmed.ncbi.nlm.nih.gov/40729722"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3593543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3593543","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065943384","display_name":"Yaozong Zheng","orcid":"https://orcid.org/0009-0007-2664-0574"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaozong Zheng","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and the Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and the Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058101262","display_name":"Bineng Zhong","orcid":"https://orcid.org/0000-0003-3423-1539"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bineng Zhong","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and the Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and the Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049287545","display_name":"Qihua Liang","orcid":"https://orcid.org/0000-0003-2353-5246"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qihua Liang","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and the Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and the Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084025984","display_name":"Shengping Zhang","orcid":"https://orcid.org/0000-0001-5200-3420"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengping Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Weihai, Shandong, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, Shandong, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100775216","display_name":"Guorong Li","orcid":"https://orcid.org/0000-0003-3954-2387"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guorong Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037037839","display_name":"Xianxian Li","orcid":"https://orcid.org/0000-0002-7083-3847"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianxian Li","raw_affiliation_strings":["Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and the Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]},{"raw_affiliation_string":"Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, and the Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University, Guilin, China","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Ji","raw_affiliation_strings":["Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China","Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Media Analytics and Computing Lab, Department of Artificial Intelligence, School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5065943384"],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":6.544,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96792615,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"47","issue":"11","first_page":"10192","last_page":"10209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.8680999875068665,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.8680999875068665,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8424000144004822,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7495999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7244206070899963},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5881814956665039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5790113210678101},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5279079079627991},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5171113014221191},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3409067690372467},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33196306228637695},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.12254443764686584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7244206070899963},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5881814956665039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5790113210678101},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5279079079627991},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5171113014221191},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3409067690372467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33196306228637695},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.12254443764686584},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3593543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3593543","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40729722","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40729722","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":82,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2158592639","https://openalex.org/W2470394683","https://openalex.org/W2557641257","https://openalex.org/W2794744029","https://openalex.org/W2799058067","https://openalex.org/W2886910176","https://openalex.org/W2891033863","https://openalex.org/W2898200825","https://openalex.org/W2917353338","https://openalex.org/W2962766617","https://openalex.org/W2963227409","https://openalex.org/W2963351448","https://openalex.org/W2963534981","https://openalex.org/W2963905288","https://openalex.org/W2964211168","https://openalex.org/W2964423614","https://openalex.org/W2966759264","https://openalex.org/W2987460522","https://openalex.org/W2990205821","https://openalex.org/W2996575194","https://openalex.org/W2998027361","https://openalex.org/W2998434318","https://openalex.org/W3001584168","https://openalex.org/W3002567850","https://openalex.org/W3034297219","https://openalex.org/W3035211844","https://openalex.org/W3035453691","https://openalex.org/W3035511673","https://openalex.org/W3035672751","https://openalex.org/W3047017093","https://openalex.org/W3090155371","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3101990647","https://openalex.org/W3104158266","https://openalex.org/W3108519869","https://openalex.org/W3110562975","https://openalex.org/W3127756064","https://openalex.org/W3158472981","https://openalex.org/W3167536469","https://openalex.org/W3167762749","https://openalex.org/W3168663926","https://openalex.org/W3172670627","https://openalex.org/W3174225630","https://openalex.org/W3175891031","https://openalex.org/W3181069167","https://openalex.org/W3202534481","https://openalex.org/W3204540098","https://openalex.org/W3209993199","https://openalex.org/W4214493665","https://openalex.org/W4214737929","https://openalex.org/W4214759957","https://openalex.org/W4283808043","https://openalex.org/W4285600988","https://openalex.org/W4289535600","https://openalex.org/W4304098539","https://openalex.org/W4312255167","https://openalex.org/W4312323989","https://openalex.org/W4312532041","https://openalex.org/W4312668764","https://openalex.org/W4312670531","https://openalex.org/W4312735552","https://openalex.org/W4312751983","https://openalex.org/W4312805142","https://openalex.org/W4313156423","https://openalex.org/W4320036905","https://openalex.org/W4320036970","https://openalex.org/W4382240192","https://openalex.org/W4385245566","https://openalex.org/W4386065544","https://openalex.org/W4386066081","https://openalex.org/W4386066266","https://openalex.org/W4386075603","https://openalex.org/W4386075647","https://openalex.org/W4386083067","https://openalex.org/W4387587572","https://openalex.org/W4393147957","https://openalex.org/W4393154934","https://openalex.org/W4402727922","https://openalex.org/W4402753948"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4285141722","https://openalex.org/W2158788032"],"abstract_inverted_index":{"We":[0,48,101],"propose":[1,102],"a":[2,54,61,95,113,129,205],"universal":[3],"video-level":[4],"modality-awareness":[5],"tracking":[6,22],"model":[7,33,39,126,191],"with":[8,42],"online":[9,78],"dense":[10,79],"temporal":[11,80,151],"token":[12,81,146],"learning":[13],"(called":[14],"UM-ODTrack).":[15],"It":[16],"is":[17,40,164],"designed":[18,41],"to":[19,53,59,84,166],"support":[20],"various":[21],"tasks,":[23],"including":[24],"RGB,":[25],"RGB+Thermal,":[26],"RGB+Depth,":[27],"and":[28,35,88,117,197],"RGB+Event,":[29],"utilizing":[30],"the":[31,50,86,122,140,154,157,185],"same":[32,123],"architecture":[34],"parameters.":[36],"Specifically,":[37],"our":[38,178,202],"three":[43],"core":[44],"goals:":[45],"Video-level":[46,69],"Sampling.":[47],"expand":[49],"model's":[51],"inputs":[52],"video":[55,63,96,159],"sequence":[56],"level,":[57],"aiming":[58],"see":[60],"richer":[62],"context":[64],"from":[65],"an":[66],"near-global":[67],"perspective.":[68],"Association.":[70],"Furthermore,":[71],"we":[72],"introduce":[73],"two":[74,103],"simple":[75],"yet":[76],"effective":[77],"association":[82],"mechanisms":[83],"propagate":[85],"appearance":[87],"motion":[89],"trajectory":[90],"information":[91,163],"of":[92,125],"target":[93],"via":[94,112,128],"stream":[97],"manner.":[98],"Modality":[99],"Scalable.":[100],"novel":[104],"gated":[105,114],"perceivers":[106],"that":[107,174,201],"adaptively":[108],"learn":[109],"cross-modal":[110],"representations":[111],"attention":[115],"mechanism,":[116],"subsequently":[118],"compress":[119],"them":[120],"into":[121],"set":[124],"parameters":[127],"one-shot":[130,179],"training":[131,180,186],"manner":[132],"for":[133,153],"multi-task":[134],"inference.":[135,169],"This":[136],"new":[137,206],"solution":[138],"brings":[139],"following":[141],"benefits:":[142],"(i)":[143],"The":[144],"purified":[145],"sequences":[147],"can":[148],"serve":[149],"as":[150],"prompts":[152],"inference":[155],"in":[156],"next":[158],"frames,":[160],"whereby":[161],"previous":[162],"leveraged":[165],"guide":[167],"future":[168],"(ii)":[170],"Unlike":[171],"multi-modal":[172,198],"trackers":[173],"require":[175],"independent":[176],"training,":[177],"scheme":[181],"not":[182],"only":[183],"alleviates":[184],"burden,":[187],"but":[188],"also":[189],"improves":[190],"representation.":[192],"Extensive":[193],"experiments":[194],"on":[195],"visible":[196],"benchmarks":[199],"show":[200],"UM-ODTrack":[203],"achieves":[204],"SOTA":[207],"performance.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}